nncf.torch.sparsity.const.algo#
Classes#
Controller for the auxiliary constant sparsity algorithm in PT. |
- class nncf.torch.sparsity.const.algo.ConstSparsityController(target_model, sparsified_module_info)[source]#
Bases:
nncf.torch.sparsity.base_algo.BaseSparsityAlgoControllerController for the auxiliary constant sparsity algorithm in PT.
- Parameters:
target_model (nncf.torch.nncf_network.NNCFNetwork) –
sparsified_module_info (List[SparseModuleInfo]) –
- freeze()[source]#
Freezes all sparsity masks. Sparsity masks will not be trained after calling this method.
- set_sparsity_level(sparsity_level)[source]#
Sets the sparsity level that should be applied to the model’s weights.
- Parameters:
sparsity_level (float) – Sparsity level that should be applied to the model’s weights.
- statistics(quickly_collected_only=False)[source]#
Returns a Statistics class instance that contains compression algorithm statistics.
- Parameters:
quickly_collected_only (bool) – Enables collection of the statistics that don’t take too much time to compute. Can be helpful for the case when need to keep track of statistics on each training batch/step/iteration.
- Return type: